Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Math Problem Solving on OlympiadBench

68.32Accuracy

LESS

4.963221.411637.8654.3084Nov 11, 2025Dec 18, 2025Jan 24, 2026Mar 2, 2026Apr 8, 2026May 15, 2026Jun 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
68.32
2026.06
68.29
2026.06
68.25
2026.06
67.62
2026.06
67.62
2026.06
67.51
2026.06
66.77
2026.06
66.58
2026.06
65.95
2026.06
60.24
2025.11
52
2025.11
50.5
2025.11
50.1
2025.11
47.7
2025.11
45
2026.06
42.83
2026.06
42.17
2026.06
41.44
2025.11
41.2
2026.06
40.61
2026.06
39.1
2025.11
38.8
2026.06
37.2
2026.06
36.31
2026.06
35.61
2026.06
35.5
2026.06
35.35
2026.06
35.27
2026.06
34.9
2026.06
34.69
2026.06
34.54
2026.06
34.31
2026.06
34.27
2026.06
33.6
2026.06
33.54
2025.11
33.4
2025.11
33
2026.06
32.34
2025.11
30.6
2025.11
30
2026.06
26.61
2026.06
26.59
2025.11
24
2026.06
24
2025.11
23.9
2025.11
19.4
2025.11
18.8
2026.06
18.02
2025.11
10.2
2025.11
7.4